초록 close

Two real-time modeling prediction (RMP) schemes are presented in this paper for analyzingthe behavior of deep excavations during construction. The first RMP scheme is developed from thetraditionalAR(p) model. The second is based on the simplified Elman-style recurrent neural networks. Anon-line learning algorithm is introduced to describe the dynamic behavior of deep excavations. As a casestudy, in-situ measurements of an excavation were recorded and the measured data were used to verifythe reliability of the two schemes. They proved to be both effective and convenient for predicting thebehavior of dep excavations during construction. It is shown through the case study that the RMPscheme based on the neural network is more acurate than that based on the traditional AR(p) model.